Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1727 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0337. Min Range: -1.0337

Max Act: 1.0337. Min Act: -0.0000

Data Index: 295416 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9714. Min Act: -0.0000

Data Index: 827290 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.9453. Min Act: -0.0000

Data Index: 357321 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8990. Min Act: -0.0000

Data Index: 50765 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7998. Min Act: -0.0000

Data Index: 703995 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7693. Min Act: -0.0000

Data Index: 1034826 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8411. Min Act: -0.0000

Data Index: 824666 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.8022. Min Act: -0.0000

Data Index: 800412 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7661. Min Act: -0.0000

Data Index: 364380 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7416. Min Act: -0.0000

Data Index: 296126 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7592. Min Act: -0.0000

Data Index: 107502 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7381. Min Act: -0.0000

Data Index: 235090 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.6850. Min Act: -0.0000

Data Index: 519238 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.7034. Min Act: -0.0000

Data Index: 967058 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.6426. Min Act: -0.0000

Data Index: 168411 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.6180. Min Act: -0.0000

Data Index: 23719 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.6122. Min Act: -0.0000

Data Index: 281228 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.6091. Min Act: -0.0000

Data Index: 529327 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.5918. Min Act: -0.0000

Data Index: 79217 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.0337. Min Range: -1.0337

Max Act: 0.5902. Min Act: -0.0000

Data Index: 205210 (C4 (Web Text))

Max Activating Token Index: 753